Capstone Project: Text Prediction Algorithm

This presentation was prepared in order to present the Capstone Project of the Data Science Specialization provided by the Johns Hopkins Bloomberg School of Public Health.

The main goal of the Capstone Project is to create a data product, a Shiny application, that demonstrates the text prediction algorithm. The Shiny application takes as input a phrase (multiple words) in a text box input and outputs a prediction of the next word.

The data used to create the text prediction algorithm and the Shiny Application was provided by the SwiftKey company and consists of the data collected from blogs, news and twitter.

This application uses the text prediction algorithm to predict the next word of the phrase that you enter in the text input box.

The next word is predicted with the use of the frequencies of combinations of two, three and four words (Digrams, Trigrams and Quadgrams).

The frequencies of words are calculated using the text extracted from blogs, news and twitter data that SwiftKey company provided for this Capstone Project.

The word 'it' is used as a default word when there are no hints for prediction

The Shiny Application is running on the Shiny Server (shinyapps.io) Please follow this link https://mbaizhanova.shinyapps.io/capstone/ in order to use the Shiny Application.

The application has text input and output boxes.

The user has to enter the words in the text box and the model would suggest the next word.

I want to thank the whole team of people that prepared this Data Science Specialization. It was a long and interesting journey for me. I am very glad that I enrolled in this specialization!

As for my plans, I am going to continue to explore the huge area of Data Science!